USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning

TL;DR

This paper introduces USE, a lightweight method for assessing unlabeled data quality in semi-supervised learning, improving robustness and accuracy by filtering out uninformative or harmful samples, especially under out-of-distribution contamination.

Contribution

USE provides a principled, model-agnostic approach to evaluate and curate unlabeled data quality, enhancing SSL performance in contaminated environments.

Findings

USE improves accuracy on CIFAR-100 and Yelp Review datasets.

USE enhances robustness against out-of-distribution contamination.

USE effectively filters uninformative unlabeled samples before training.

Abstract

In this study, a novel idea, Uncertainty Structure Estimation (USE), a lightweight, algorithm-agnostic procedure that emphasizes the often-overlooked role of unlabeled data quality is introduced for Semi-supervised learning (SSL). SSL has achieved impressive progress, but its reliability in deployment is limited by the quality of the unlabeled pool. In practice, unlabeled data are almost always contaminated by out-of-distribution (OOD) samples, where both near-OOD and far-OOD can negatively affect performance in different ways. We argue that the bottleneck does not lie in algorithmic design, but rather in the absence of principled mechanisms to assess and curate the quality of unlabeled data. The proposed USE trains a proxy model on the labeled set to compute entropy scores for unlabeled samples, and then derives a threshold, via statistical comparison against a reference distribution, that separates informative (structured) from uninformative (structureless) samples. This enables assessment as a preprocessing step, removing uninformative or harmful unlabeled data before SSL training begins. Through extensive experiments on imaging (CIFAR-100) and NLP (Yelp Review) data, it is evident that USE consistently improves accuracy and robustness under varying levels of OOD contamination. Thus, it can be concluded that the proposed approach reframes unlabeled data quality control as a structural assessment problem, and considers it as a necessary component for reliable and efficient SSL in realistic mixed-distribution environments.